Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 1048 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.3167. Min Range: -0.3167

Max Act: 0.3024. Min Act: -0.0000

Data Index: 723538 (C4 (Web Text))

Max Activating Token Index: 542

Text #1

Max Range: 0.3167. Min Range: -0.3167

Max Act: 0.3090. Min Act: -0.0000

Data Index: 884769 (C4 (Web Text))

Max Activating Token Index: 334

Text #2

Max Range: 0.3167. Min Range: -0.3167

Max Act: 0.3167. Min Act: -0.0000

Data Index: 159489 (C4 (Web Text))

Max Activating Token Index: 465

Text #3

Max Range: 0.3167. Min Range: -0.3167

Max Act: 0.2976. Min Act: -0.0001

Data Index: 387268 (C4 (Web Text))

Max Activating Token Index: 659

Text #4

Max Range: 0.3167. Min Range: -0.3167

Max Act: 0.2871. Min Act: -0.0001

Data Index: 1068582 (C4 (Web Text))

Max Activating Token Index: 364

Text #5

Max Range: 0.3167. Min Range: -0.3167

Max Act: 0.2755. Min Act: -0.0000

Data Index: 188963 (C4 (Web Text))

Max Activating Token Index: 351

Text #6

Max Range: 0.3167. Min Range: -0.3167

Max Act: 0.3069. Min Act: -0.0000

Data Index: 535995 (C4 (Web Text))

Max Activating Token Index: 906

Text #7

Max Range: 0.3167. Min Range: -0.3167

Max Act: 0.3046. Min Act: -0.0001

Data Index: 1193874 (C4 (Web Text))

Max Activating Token Index: 489

Text #8

Max Range: 0.3167. Min Range: -0.3167

Max Act: 0.2928. Min Act: -0.0001

Data Index: 157483 (C4 (Web Text))

Max Activating Token Index: 388

Text #9

Max Range: 0.3167. Min Range: -0.3167

Max Act: 0.2879. Min Act: -0.0000

Data Index: 294710 (C4 (Web Text))

Max Activating Token Index: 159

Text #10

Max Range: 0.3167. Min Range: -0.3167

Max Act: 0.2855. Min Act: -0.0000

Data Index: 119633 (C4 (Web Text))

Max Activating Token Index: 101

Text #11

Max Range: 0.3167. Min Range: -0.3167

Max Act: 0.2772. Min Act: -0.0001

Data Index: 1262400 (C4 (Web Text))

Max Activating Token Index: 632

Text #12

Max Range: 0.3167. Min Range: -0.3167

Max Act: 0.2560. Min Act: -0.0001

Data Index: 406200 (C4 (Web Text))

Max Activating Token Index: 326

Text #13

Max Range: 0.3167. Min Range: -0.3167

Max Act: 0.2578. Min Act: -0.0001

Data Index: 1213300 (C4 (Web Text))

Max Activating Token Index: 578

Text #14

Max Range: 0.3167. Min Range: -0.3167

Max Act: 0.2567. Min Act: -0.0001

Data Index: 1113560 (C4 (Web Text))

Max Activating Token Index: 885

Text #15

Max Range: 0.3167. Min Range: -0.3167

Max Act: 0.2404. Min Act: -0.0001

Data Index: 301760 (C4 (Web Text))

Max Activating Token Index: 1005

Text #16

Max Range: 0.3167. Min Range: -0.3167

Max Act: 0.2546. Min Act: -0.0000

Data Index: 1121691 (C4 (Web Text))

Max Activating Token Index: 41

Text #17

Max Range: 0.3167. Min Range: -0.3167

Max Act: 0.2600. Min Act: -0.0000

Data Index: 1171137 (C4 (Web Text))

Max Activating Token Index: 705

Text #18

Max Range: 0.3167. Min Range: -0.3167

Max Act: 0.2409. Min Act: -0.0000

Data Index: 49875 (C4 (Web Text))

Max Activating Token Index: 944

Text #19

Max Range: 0.3167. Min Range: -0.3167

Max Act: 0.2505. Min Act: -0.0000

Data Index: 545695 (C4 (Web Text))

Max Activating Token Index: 94